Image Anomaly Detection with Generative Adversarial Networks

• Published in: Machine Learning and Knowledge Discovery in Databases Vol. 11051; pp. 3 - 17
• Main Authors: Deecke, Lucas, Vandermeulen, Robert, Ruff, Lukas, Mandt, Stephan, Kloft, Marius
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2019; Springer International Publishing
• Series: Lecture Notes in Computer Science
• ISBN: 9783030109240; 3030109240
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-10925-7_1

Many anomaly detection methods exist that perform well on low-dimensional problems however there is a notable lack of effective methods for high-dimensional spaces, such as images. Inspired by recent successes in deep learning we propose a novel approach to anomaly detection using generative adversarial networks. Given a sample under consideration, our method is based on searching for a good representation of that sample in the latent space of the generator; if such a representation is not found, the sample is deemed anomalous. We achieve state-of-the-art performance on standard image benchmark datasets and visual inspection of the most anomalous samples reveals that our method does indeed return anomalies.